© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16821
    Prev
    Next
    INDEX
    Explanations

    backward compatibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     have
    0.60
    ；
    0.60
     as
    0.56
    ط
    0.55
     boa
    0.54
     coexist
    0.53
     część
    0.53
    ，
    0.53
    ש
    0.51
    ק
    0.51
    POSITIVE LOGITS
    backward
    0.60
    rogation
    0.60
    Backward
    0.57
    вання
    0.55
    ğini
    0.52
    ı
    0.52
    ventory
    0.51
    ги
    0.50
    𝟮
    0.49
    ront
    0.48
    Activations Density 0.000%

    No Known Activations